Abstract
Cancer remains a global health challenge due to high morbidity, mortality, and tumor heterogeneity. Conventional diagnostic and therapeutic approaches are often insufficient, causing a shift in the paradigm toward personalized medicine. Bioinformatics, by integrating genomic, transcriptomic, proteomic, imaging, and clinical data, has become pivotal in precision oncology, enabling biomarker discovery, individualized therapy, and prognostic assessment. This systematic review followed PRISMA guidelines. PubMed, Scopus, Web of Science, and Google Scholar were searched up to May 2025. Eligible studies examined bioinformatics applications in cancer diagnosis, prognosis, or treatment personalization. Two independent reviewers performed screening and data extraction across 12 domains, including cancer type, study design, tools, findings, and challenges. Narrative synthesis and descriptive statistics were applied, and 18 studies from 8,133 records were included. Breast, lung, and liver cancers were most frequently investigated, respectively. The United States, Iran, and China were leading contributors. Commonly used platforms included TCGA, GEO, ENCODE, Cytoscape, STRING, and Reactome. Key biomarkers were TRIP13, STIL, NTRK2/3, FGFR2, VEGFA, and non-coding RNAs. Support vector machines, convolutional neural networks, LASSO regression, and deep learning achieved predictive accuracies of 85–95% for tumor subtyping, survival, and treatment response. The integration of multi-omics and imaging enhanced diagnostic precision and therapeutic stratification. Bioinformatics-driven personalized oncology is transitioning into clinical reality, improving biomarker discovery and individualized therapy. However, translation remains constrained by data standardization, interoperability, limited genomic diversity, and algorithm interpretability. Future research should prioritize explainable AI, federated learning, standardized multi-omic datasets, and international collaboration to ensure equitable, reproducible, and clinically meaningful precision oncology.